{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T13:57:57Z","timestamp":1791467877964,"version":"4.3.4"},"posted":{"date-parts":[[2026]]},"group-title":"SSRN","reference-count":0,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.uspto.gov\/ip-policy\/copyright-policy\/copyright-basics"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>We study whether bullish price-rejection patterns at multi-timeframe wick trendlines predict favourable price excursions in U.S. equities, and whether the predictability survives realistic implementation. The patterns formalize the author's discretionary chart reading; the study does not isolate what their geometry adds beyond the classifier. The motivating mechanism, resting limit orders absorbing impatient flow, is a hypothesis: our data are daily bars. Relative to a training window ending in July 2022, an estimated probability index discriminates realized outcomes (AUC 0.686, above one half in all 17 evaluable months), but so does volatility alone (0.700): most of the pooled discrimination is volatility. Within volatility quintiles the index's monthly AUC averages 0.604, and within instruments 0.537: a real but modest contribution. Three hypothetical model portfolios earn net-of-cost Jensen alphas of 63.1%, 16.8% and 32.3% per year (t = 4.9, 2.0, 2.0; HAC errors), but the edge is capacity-limited: Portfolios A and C trade names with median daily dollar volume of about $5 and $4 million, and Portfolio A's return on capital halves at roughly $25 million of simulated net asset value. Only Portfolio A survives deflation for selection across configurations and a high survivorship haircut. Most scoring was performed in batch, and in the 79-day real-time window, too short to be informative, none of the portfolios outperforms, so we treat the performance results as hypotheses. The evidence is inconsistent with semi-strong efficiency under the joint-hypothesis caveat; it does not falsify it, and we pre-register the forward test with explicit refutation criteria.<\/jats:p>","DOI":"10.2139\/ssrn.7578878","type":"posted-content","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T13:13:32Z","timestamp":1791465212000},"source":"Crossref","is-referenced-by-count":0,"title":["Reading the Wicks: A Candidate Trendline-Rejection Anomaly in U.S. Equities, with Out-of-Sample Machine-Learning Evidence"],"prefix":"10.2139","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6085-3003","authenticated-orcid":true,"given":"Alejandro","family":"Casamayor","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T13:13:33Z","timestamp":1791465213000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=7578878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":0,"URL":"https:\/\/doi.org\/10.2139\/ssrn.7578878","relation":{},"subject":[],"published":{"date-parts":[[2026]]},"subtype":"preprint"}}